EVA 2006 - Cruscle search engine

This paper presents the advanced search tecniques implemented for the Accademia della Crusca on-line vocabularies. The five vocabularies represent the origin and evolution of the Italian language during the last centuries. They have been completely transcripted and annotated in a standard XML/TEI format. The transcription has been indexed with a complex structure that allows advanced search queries, including: full text query, context and micro- context queries, case sensitiveness, accented characters, search of word roots and punctuation marks. The search algorithms are based on the open source indexing and search engine Apache Lucene with heavy modifications.

Download PDF

IEEE Multimedia 2005 - Natural Interfaces

The authors present a multimedia system that really works in a cultural public space. Indeed, if you go to Florence and visit the museum of Palazzo Medici Riccardi, you might see a queue of worldwidetourists waiting for their turn to play with a digital version of the famous fresco The Journey of the Magi, appearing on two large screens. Visitors stand in front of the screens and point with their hands to the part of the painting theyĆ½re interested in. Two cameras grab this point and analgorithm calculates the exact part of the painting the person selected. In response to the pointing, an audio response gives information on the subjects or objects. Visitors seem to deeply enjoy theirinteraction with the system, which does feel natural. Visitors wear no special equipment and use no complex hardware; the fresco is extremely well displayed, and typically the information is precise and interesting, with different levels of information available.

Link to ACM Portal reference.

ICPR 2004 - Motion capture

In this paper a composite framework for collaborative working is presented. The framework includes real-time motion tracking based on computer vision from standard webcams situated at different locations, data transmission and real-time animation of 3D avatars in a virtual world. Motion tracking is obtained without using markers, with weak constraints on users' clothes and environment lighting. It is based on a model fitting process that compares the 2D processed images supplied by cameras with a set of artificially generated views of a human model.

Link to ACM Portal reference.